
Ransack MCP Server認証済み注目
@chancewalker165-dot
基本情報
Ransack MCP Server について
Every SERP, every extractor. One MCP: search, page fetch, cited research, transcripts, product prices and permit records for AI agents, with the source URL on every result.


Ransack MCP Server の設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"ransack": {
"type": "streamable-http",
"url": "https://ransack.tools/mcp",
"headers": {
"Authorization": "Bearer <API_KEY>"
}
}
}
}Ransack MCP Server のツール
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンでサーバーのエンドポイントに接続し、ツール一覧を取得できます。
概要
Every SERP, every extractor. One MCP.
Live search, page fetch and cited research for AI agents, from one MCP endpoint, with a source URL on every result and the finding engine named on every search result.
This is a hosted service. This repository contains connection configuration, documentation and logo only; the server source is not public. Connect to:
https://ransack.tools/mcp
- Homepage: ransack.tools
- Free trial key: ransack.tools/trial
Connect
Get an API key from ransack.tools/trial, then add the server to your client.
Claude Desktop
{"mcpServers":{"ransack":{"type":"streamable-http","url":"https://ransack.tools/mcp","headers":{"Authorization":"Bearer <API_KEY>"}}}}
Cursor
{"mcpServers":{"ransack":{"url":"https://ransack.tools/mcp","headers":{"Authorization":"Bearer <API_KEY>"}}}}
Pi / Cline / 5ire
{"mcpServers":{"ransack":{"type":"http","url":"https://ransack.tools/mcp","headers":{"Authorization":"Bearer <API_KEY>"}}}}
Transport is streamable-http; authentication is a Bearer API key.
Tools (6)
| Tool | What it does |
|---|---|
ransack | The main tool. Modes: search, fetch, discover, hosts (7 keyless discovery sources), shop, verify, help. Markdown / JSON / hybrid output. Every result is tagged with the engine that found it. |
youtube | Retrieve a YouTube transcript from a video URL or video ID (not a keyword search). |
tasks_get | Retrieve the status and result of an asynchronous task started with background=true. |
get_report | Retrieve a persisted research report and its citation map by report_id (legacy: reports produced before the research lane was retired 2026-09-20). |
search_memory | Semantic recall over previously fetched page chunks (pages, articles, transcripts). Not conversational history. |
ransack_permit_search | US government permit lookup by street address (currently Brevard County FL Accela: building permits incl. roofing/fence/pool, status, contractor). Keyless, no browser, no captcha. |
ransack
One tool, many modes. search is metasearch across engines; fetch is the
primary answer path (paste a URL, get the extracted page); discover and
hosts enumerate a domain's assets from certificate transparency, DNS,
sitemaps, web archives, crawl indexes, JS routes and scan records; shop
returns price and availability; verify checks a claim against its cited
sources; help returns the full manual. freshness bypasses the result
cache; it does not date-filter.
youtube
Fetch a YouTube transcript from a video URL or video ID.
ransack_permit_search
Search US permit portals by street address. Currently Brevard County FL (Accela Citizen Access), building permits including roofing, fence and pool work types, status and contractor. Keyless and captcha-free.
What you actually get back
- Engine-tagged results. Every search result names the engine that found it, so you can tell Google from an independent index.
- Coverage status, not silence. On
hosts, every discovery engine reportsok,empty,timeoutorskipped. Found-nothing is never indistinguishable from tried-and-failed. - Labelled walls.
[bot wall: <vendor>]and[dead page: HTTP 404]come back as labels. Pages the server cannot read are reported, not guessed. - No query rewrites. Ever. The caller owns site selection. Ransack never appends operators to your query or silently changes what you asked for.
- One key, six tools. Search, fetch, discovery, shopping, transcripts and permit records behind a single endpoint.
Honest limitations
- Paywalled and login-walled pages (e.g. some news, GitHub
/commitsviews) can't always be read. - Retailers that hard-block scraping (Amazon, Walmart) may return nothing rather than guessed data.
- TikTok is searchable and the snippet carries the caption; the video, comments and spoken transcript do not come back.
searchfast-lane results are partial by design;fetchis the primary answer path.- Labelling is not guaranteed: a wall sometimes comes back as thin page content instead.
Pricing & limits
- Trial: free for 14 days, 50 calls/day, 60 requests/min, no card (ransack.tools/trial).
- Paid: $15/month flat, 500 calls/day, 120 requests/min.
License
This repository is documentation and configuration only. The service at
ransack.tools is proprietary.
「検索」の他のコンテンツ
VarynForge
VarynForgeVarynForge is an SEO research SaaS that exposes its full workflow as MCP tools. Connect once from Claude Desktop, Claude Code, Cursor, Codex or any MCP host, then ask your agent to set up a project, hand it your article

Sorank
Thibault Besson-MagdelainSorank connects Google Search Console, PageSpeed Insights, and AI citability scoring to your assistant, so it can diagnose why a page underperforms and tell you exactly what to change. Sorank gives your AI assistant dir
Goalie Trademark Search MCP
goalie-mcpSearch & filter 14M+ USPTO trademark records from an AI agent. This is a trademark MCP server, not a TSDR lookup.

Aguasto Research
AguastoOfficial read-only MCP access to Aguasto's public GPU, model and infrastructure research. Search published descriptions and retrieve canonical source links. Anonymous Streamable HTTP; GPU rental and token-based inference
SaaS Think Tank — Software Research
SaaS Think TankSoftware research to help people choose the right tools. SaaS Think Tank publishes software comparisons, reviews and practical resources across categories, with dated findings, source links and clear limits. Current MCP
コメント